commit 1708045ba322f4da3d170bc7b2b54cf0c77c63ef Author: ModelHub XC Date: Thu Aug 20 02:13:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Phi-1.5-Tele-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5459e75 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-1.5-Tele.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi-1.5-Tele.i1-IQ1_M.gguf b/Phi-1.5-Tele.i1-IQ1_M.gguf new file mode 100644 index 0000000..16d6d9d --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa8abad42a6e44edc8946a703a50c7fd7a763f4116f69eabec92bac09b237a94 +size 395376064 diff --git a/Phi-1.5-Tele.i1-IQ1_S.gguf b/Phi-1.5-Tele.i1-IQ1_S.gguf new file mode 100644 index 0000000..c9a24e7 --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8889acd9557456ac371694276049c57f6e74bdb11c3c28da77d7cc5b03dbc69 +size 372962752 diff --git a/Phi-1.5-Tele.i1-IQ2_M.gguf b/Phi-1.5-Tele.i1-IQ2_M.gguf new file mode 100644 index 0000000..04dad9e --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cfc51985157088d9bb002744f286a99bbb9db4ac7a98835db5d7d41b946061e +size 535786944 diff --git a/Phi-1.5-Tele.i1-IQ2_S.gguf b/Phi-1.5-Tele.i1-IQ2_S.gguf new file mode 100644 index 0000000..c1ec917 --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b718850437598a7948c56d642882e61836ca065b42645e299e25f09a8ea4ba +size 505902528 diff --git a/Phi-1.5-Tele.i1-IQ2_XS.gguf b/Phi-1.5-Tele.i1-IQ2_XS.gguf new file mode 100644 index 0000000..01235fc --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c10cecddfde0b9f4ca8f81811455cd9aa1d19fe4a22c8bd24ac331e0743e3c7a +size 465761728 diff --git a/Phi-1.5-Tele.i1-IQ2_XXS.gguf b/Phi-1.5-Tele.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..13388bd --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cb4049125508869b065d286d618e8b6b1deb436071300a6c55e44940cf208c6 +size 432731584 diff --git a/Phi-1.5-Tele.i1-IQ3_M.gguf b/Phi-1.5-Tele.i1-IQ3_M.gguf new file mode 100644 index 0000000..048a5df --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a8ab08f3d4e526a6dd33c892754a659ab7b38391da96232cab7158d9fed40d +size 687732160 diff --git a/Phi-1.5-Tele.i1-IQ3_S.gguf b/Phi-1.5-Tele.i1-IQ3_S.gguf new file mode 100644 index 0000000..8e348ec --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6163474dce93f9ca4f3ce64a2408355b3795326c8cf1499de6e40ffca1be4cd3 +size 654308800 diff --git a/Phi-1.5-Tele.i1-IQ3_XS.gguf b/Phi-1.5-Tele.i1-IQ3_XS.gguf new file mode 100644 index 0000000..08fc774 --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a82b2cfae43d1b061378e509c1c3e6c0a35abd452e529b817f9595606036d1 +size 630715840 diff --git a/Phi-1.5-Tele.i1-IQ3_XXS.gguf b/Phi-1.5-Tele.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..b248565 --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60089945f330b5cbfab062207b008dfc16a231f71452388c4c4d650117f5a240 +size 575894976 diff --git a/Phi-1.5-Tele.i1-IQ4_NL.gguf b/Phi-1.5-Tele.i1-IQ4_NL.gguf new file mode 100644 index 0000000..a3dbdb0 --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcb6bf58b19602c150a1d48a05a6ae046c5d83b51ab3bc31498ded579ed5aab8 +size 828667328 diff --git a/Phi-1.5-Tele.i1-IQ4_XS.gguf b/Phi-1.5-Tele.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b8f48aa --- /dev/null +++ b/Phi-1.5-Tele.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8545629be5d31fe77edcb69434f9c43ecdc4f9b9a9534e1144909c722a4afc2f +size 787641792 diff --git a/Phi-1.5-Tele.i1-Q2_K.gguf b/Phi-1.5-Tele.i1-Q2_K.gguf new file mode 100644 index 0000000..0b803a0 --- /dev/null +++ b/Phi-1.5-Tele.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb7585ef17645e6255d5100a3f99084ea186000306b7db14626990873a2bdd50 +size 582317504 diff --git a/Phi-1.5-Tele.i1-Q2_K_S.gguf b/Phi-1.5-Tele.i1-Q2_K_S.gguf new file mode 100644 index 0000000..8c78409 --- /dev/null +++ b/Phi-1.5-Tele.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a326054ad359f084cc435e20eaa895521458daa5eb90c85ad2f777814c691ecb +size 532772288 diff --git a/Phi-1.5-Tele.i1-Q3_K_L.gguf b/Phi-1.5-Tele.i1-Q3_K_L.gguf new file mode 100644 index 0000000..aee174d --- /dev/null +++ b/Phi-1.5-Tele.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba84bc8d1b558e45b36ce849cab8d62ca9be5b46877037a246b91206f05b7f6 +size 810022336 diff --git a/Phi-1.5-Tele.i1-Q3_K_M.gguf b/Phi-1.5-Tele.i1-Q3_K_M.gguf new file mode 100644 index 0000000..3bc6353 --- /dev/null +++ b/Phi-1.5-Tele.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feca9b431355b7fa087f589df9042769485ae1817245e064f8f3222b7a38efb8 +size 737670592 diff --git a/Phi-1.5-Tele.i1-Q3_K_S.gguf b/Phi-1.5-Tele.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ce3504c --- /dev/null +++ b/Phi-1.5-Tele.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a9b19478f7449e3d38d7ab717b7bee2f23897d61d4f873563eaeb711ac38dea +size 654308800 diff --git a/Phi-1.5-Tele.i1-Q4_0.gguf b/Phi-1.5-Tele.i1-Q4_0.gguf new file mode 100644 index 0000000..407c50f --- /dev/null +++ b/Phi-1.5-Tele.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:839940cf02aabbd9ecfa63a86178f6a09b6f468127e33d330266ae3cabe938a7 +size 831813056 diff --git a/Phi-1.5-Tele.i1-Q4_1.gguf b/Phi-1.5-Tele.i1-Q4_1.gguf new file mode 100644 index 0000000..14c0e0c --- /dev/null +++ b/Phi-1.5-Tele.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350e0a35f4901eedb01dbe04860aec0ebff5ea181e5d388065552bb91594a0c7 +size 910718400 diff --git a/Phi-1.5-Tele.i1-Q4_K_M.gguf b/Phi-1.5-Tele.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ca60f49 --- /dev/null +++ b/Phi-1.5-Tele.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fa50d090cb52d30f476d3ce26d0749ae55ad0b8e0b7dbaf6800428f145c64e0 +size 893547968 diff --git a/Phi-1.5-Tele.i1-Q4_K_S.gguf b/Phi-1.5-Tele.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4602bc3 --- /dev/null +++ b/Phi-1.5-Tele.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4671278ceb8c9853e2d76ac93f8913c12c4adc79e71aba53f860856dc066dc2c +size 837055936 diff --git a/Phi-1.5-Tele.i1-Q5_K_M.gguf b/Phi-1.5-Tele.i1-Q5_K_M.gguf new file mode 100644 index 0000000..092e2f2 --- /dev/null +++ b/Phi-1.5-Tele.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:723ba5398f763619271a582882b097f2010ba8d5db4305567ec02d5e6c700bd9 +size 1026192832 diff --git a/Phi-1.5-Tele.i1-Q5_K_S.gguf b/Phi-1.5-Tele.i1-Q5_K_S.gguf new file mode 100644 index 0000000..29a3b65 --- /dev/null +++ b/Phi-1.5-Tele.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4cdad214170fbdce64ca86348e5d6c3211ff0f3734f2ce5f58f9849174cc6a8 +size 992769472 diff --git a/Phi-1.5-Tele.i1-Q6_K.gguf b/Phi-1.5-Tele.i1-Q6_K.gguf new file mode 100644 index 0000000..aaaca11 --- /dev/null +++ b/Phi-1.5-Tele.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f7554880f81dedb10a22876c06671c9da5f4c5ae6c60930371c6e667050d078 +size 1167128000 diff --git a/Phi-1.5-Tele.imatrix.gguf b/Phi-1.5-Tele.imatrix.gguf new file mode 100644 index 0000000..11b4654 --- /dev/null +++ b/Phi-1.5-Tele.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f48a680d69f0cdc462ac614b667c8899cf533d242ec8794fcb17311ab87835d1 +size 1791648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bec623a --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: AliMaatouk/Phi-1.5-Tele +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- nlp +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/AliMaatouk/Phi-1.5-Tele + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Phi-1.5-Tele-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Phi-1.5-Tele-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ1_S.gguf) | i1-IQ1_S | 0.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ1_M.gguf) | i1-IQ1_M | 0.5 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ2_S.gguf) | i1-IQ2_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ2_M.gguf) | i1-IQ2_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q2_K.gguf) | i1-Q2_K | 0.7 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ3_S.gguf) | i1-IQ3_S | 0.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ3_M.gguf) | i1-IQ3_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.8 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q4_0.gguf) | i1-Q4_0 | 0.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q4_1.gguf) | i1-Q4_1 | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q5_K_S.gguf) | i1-Q5_K_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q5_K_M.gguf) | i1-Q5_K_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-1.5-Tele-i1-GGUF/resolve/main/Phi-1.5-Tele.i1-Q6_K.gguf) | i1-Q6_K | 1.3 | practically like static Q6_K | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +